learning_rate: 0.0003
train_batch_size: 4
eval_batch_size: 4
seed: 0
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1 Binary	Accuracy
No log	0	0	0.7028	0.2437	0.7160	0.3636	0.3556
0.6	2.8181	1000	0.5779	0.0	0.0	0.0	0.7429
0.5522	5.6347	2000	0.5709	0.0	0.0	0.0	0.7429
0.5582	8.4513	3000	0.5709	0.0	0.0	0.0	0.7429
0.5791	11.2680	4000	0.5703	0.0	0.0	0.0	0.7429
0.5895	14.0846	5000	0.5701	0.0	0.0	0.0	0.7429
0.5629	16.9027	6000	0.5730	0.0	0.0	0.0	0.7429
0.5841	19.7193	7000	0.5723	0.0	0.0	0.0	0.7429

babypoby/classify

classify